Marmot, context layer for agents and humans
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
Hi HN, Bruno here, one of the two people building this.For years we got away with poor context because people fill gaps. If you didn't know what a column meant or where a database lived, you asked someone. You knew who to go to. That informal layer, who to ask and what things mean, carried us for years. Agents can't do that. An agent only knows what you hand it. It doesn't ask, it guesses. So what people carried in their heads now has to live somewhere a machine can reach: what your data is, what it means, who owns it, what it connects to.Concretely, Marmot is a catalog. It catalogs your services, APIs, queues, topics, databases, pipelines, and more, then exposes that over a built-in MCP server for agents and a UI/API for people. You populate it from Terraform, Kubernetes, Pulumi, the API or the CLI.MIT licensed. Self-host for free.
HN · launched Jun 29, 2026 · 17 upvotes (top 28%) · 0 views
Niche: knowledge base and graph software · 107 launches, 1 in the last 7 days · Explore this niche →
Category and tags
- Horizontal
- Data infrastructure
- Developer
- AI-native
- Commercial product
Visit website ↗ Source listing ↗
More like this: all 107 launches in knowledge base and graph software →
Could you build this?
Partial The web UI catalog and MCP server endpoint are straightforward to vibe-code, but parsing metadata and building live lineage graphs across dozens of disparate data platforms is a massive systems undertaking.
What it would actually take: A complete version requires a distributed metadata ingestion pipeline written in Go or Python, backed by a graph database (like Neo4j) to model asset lineage and relationships. The hard part is building and maintaining 70+ specialized connectors that extract schemas, permissions, and query logs across diverse databases, message queues, and cloud compute systems.
Discussion
4 comments analyzed.
Concerns raised: Model reliability drilling down from summary to specific results, Tool selection accuracy decreases with dozens of tools, Query formulation complexity as a chokepoint
Feature requests: Scoping/search step to reduce tool selection from catalog, Integration with build and test tools in coding environments
Competitors
Other products that read as similar to this one : 98 launches clear the similarity bar, closest 8 shown.
Attention rank: #40 of 99 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 235 days after the earliest competitor.
- Airbyte Agents · hn · 2026-05-05 · 156 upvotes · similarity 0.45
- Syngraphe · ph · 2026-09-14 · 3 upvotes · similarity 0.42
- Marmot v2.20 · hn · 2025-12-12 · 5 upvotes · similarity 0.42
- proxy · github · 2026-10-06 · 65 upvotes · similarity 0.40
- Monospace from Directus · ph · 2026-10-01 · 394 upvotes · similarity 0.38
- Agent Commons · ph · 2026-09-23 · 1 upvotes · similarity 0.38
- MARVIS · ph · 2026-09-13 · 10 upvotes · similarity 0.37
- AgentKey · ph · 2026-07-13 · 416 upvotes · similarity 0.36
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.